Extracting and Visualizing Trust Relationships from Online Auction Feedback Comments

John O’Donovan, Barry Smyth, Vesile Evrim, Dennis McLeod

Buyers and sellers in online auctions are faced with the task of deciding who to entrust their business to based on a very limited amount of information. Current trust ratings on eBay average over 99 percent positive and are presented as a single number on a user profile. This paper presents a system capable of extracting valuable negative information from the wealth of feedback comments on eBay, computing personalized and feature-based trust and presenting this information graphically.